Object-based multimedia content description schemes and applications for MPEG-7
Identifieur interne : 000685 ( Istex/Corpus ); précédent : 000684; suivant : 000686Object-based multimedia content description schemes and applications for MPEG-7
Auteurs : Ana B. Benitez ; Seungyup Paek ; Shih-Fu Chang ; Atul Puri ; Qian Huang ; John R. Smith ; Chung-Sheng Li ; Lawrence D. Bergman ; Charles N. JudiceSource :
- Signal Processing: Image Communication [ 0923-5965 ] ; 2000.
Abstract
In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.
Url:
DOI: 10.1016/S0923-5965(00)00030-8
Links to Exploration step
ISTEX:1FA901B770A0A97539A87D23170665B3489A0F54Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Object-based multimedia content description schemes and applications for MPEG-7</title><author><name sortKey="Benitez, Ana B" sort="Benitez, Ana B" uniqKey="Benitez A" first="Ana B" last="Benitez">Ana B. Benitez</name><affiliation><mods:affiliation>E-mail: ana@ee.columbia.edu</mods:affiliation></affiliation><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Paek, Seungyup" sort="Paek, Seungyup" uniqKey="Paek S" first="Seungyup" last="Paek">Seungyup Paek</name><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Chang, Shih Fu" sort="Chang, Shih Fu" uniqKey="Chang S" first="Shih-Fu" last="Chang">Shih-Fu Chang</name><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Puri, Atul" sort="Puri, Atul" uniqKey="Puri A" first="Atul" last="Puri">Atul Puri</name><affiliation><mods:affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</mods:affiliation></affiliation></author><author><name sortKey="Huang, Qian" sort="Huang, Qian" uniqKey="Huang Q" first="Qian" last="Huang">Qian Huang</name><affiliation><mods:affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</mods:affiliation></affiliation></author><author><name sortKey="Smith, John R" sort="Smith, John R" uniqKey="Smith J" first="John R" last="Smith">John R. Smith</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Li, Chung Sheng" sort="Li, Chung Sheng" uniqKey="Li C" first="Chung-Sheng" last="Li">Chung-Sheng Li</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Bergman, Lawrence D" sort="Bergman, Lawrence D" uniqKey="Bergman L" first="Lawrence D" last="Bergman">Lawrence D. Bergman</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Judice, Charles N" sort="Judice, Charles N" uniqKey="Judice C" first="Charles N" last="Judice">Charles N. Judice</name><affiliation><mods:affiliation>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:1FA901B770A0A97539A87D23170665B3489A0F54</idno><date when="2000" year="2000">2000</date><idno type="doi">10.1016/S0923-5965(00)00030-8</idno><idno type="url">https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000685</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Object-based multimedia content description schemes and applications for MPEG-7</title><author><name sortKey="Benitez, Ana B" sort="Benitez, Ana B" uniqKey="Benitez A" first="Ana B" last="Benitez">Ana B. Benitez</name><affiliation><mods:affiliation>E-mail: ana@ee.columbia.edu</mods:affiliation></affiliation><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Paek, Seungyup" sort="Paek, Seungyup" uniqKey="Paek S" first="Seungyup" last="Paek">Seungyup Paek</name><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Chang, Shih Fu" sort="Chang, Shih Fu" uniqKey="Chang S" first="Shih-Fu" last="Chang">Shih-Fu Chang</name><affiliation><mods:affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</mods:affiliation></affiliation></author><author><name sortKey="Puri, Atul" sort="Puri, Atul" uniqKey="Puri A" first="Atul" last="Puri">Atul Puri</name><affiliation><mods:affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</mods:affiliation></affiliation></author><author><name sortKey="Huang, Qian" sort="Huang, Qian" uniqKey="Huang Q" first="Qian" last="Huang">Qian Huang</name><affiliation><mods:affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</mods:affiliation></affiliation></author><author><name sortKey="Smith, John R" sort="Smith, John R" uniqKey="Smith J" first="John R" last="Smith">John R. Smith</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Li, Chung Sheng" sort="Li, Chung Sheng" uniqKey="Li C" first="Chung-Sheng" last="Li">Chung-Sheng Li</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Bergman, Lawrence D" sort="Bergman, Lawrence D" uniqKey="Bergman L" first="Lawrence D" last="Bergman">Lawrence D. Bergman</name><affiliation><mods:affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</mods:affiliation></affiliation></author><author><name sortKey="Judice, Charles N" sort="Judice, Charles N" uniqKey="Judice C" first="Charles N" last="Judice">Charles N. Judice</name><affiliation><mods:affiliation>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Signal Processing: Image Communication</title><title level="j" type="abbrev">IMAGE</title><idno type="ISSN">0923-5965</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000">2000</date><biblScope unit="volume">16</biblScope><biblScope unit="issue">1–2</biblScope><biblScope unit="page" from="235">235</biblScope><biblScope unit="page" to="269">269</biblScope></imprint><idno type="ISSN">0923-5965</idno></series><idno type="istex">1FA901B770A0A97539A87D23170665B3489A0F54</idno><idno type="DOI">10.1016/S0923-5965(00)00030-8</idno><idno type="PII">S0923-5965(00)00030-8</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0923-5965</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>Ana B Benitez</name><affiliations><json:string>E-mail: ana@ee.columbia.edu</json:string><json:string>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</json:string></affiliations></json:item><json:item><name>Seungyup Paek</name><affiliations><json:string>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</json:string></affiliations></json:item><json:item><name>Shih-Fu Chang</name><affiliations><json:string>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</json:string></affiliations></json:item><json:item><name>Atul Puri</name><affiliations><json:string>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</json:string></affiliations></json:item><json:item><name>Qian Huang</name><affiliations><json:string>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</json:string></affiliations></json:item><json:item><name>John R Smith</name><affiliations><json:string>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</json:string></affiliations></json:item><json:item><name>Chung-Sheng Li</name><affiliations><json:string>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</json:string></affiliations></json:item><json:item><name>Lawrence D Bergman</name><affiliations><json:string>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</json:string></affiliations></json:item><json:item><name>Charles N Judice</name><affiliations><json:string>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>MPEG-7</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Multimedia description scheme</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Multimedia representation</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Object-based description</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Multimedia</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Image</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Video</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Home media</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Archive</value></json:item></subject><language><json:string>eng</json:string></language><abstract>In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.</abstract><qualityIndicators><score>8</score><pdfVersion>1.2</pdfVersion><pdfPageSize>504 x 672 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>9</keywordCount><abstractCharCount>1923</abstractCharCount><pdfWordCount>13460</pdfWordCount><pdfCharCount>86093</pdfCharCount><pdfPageCount>35</pdfPageCount><abstractWordCount>270</abstractWordCount></qualityIndicators><title>Object-based multimedia content description schemes and applications for MPEG-7</title><pii><json:string>S0923-5965(00)00030-8</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>16</volume><pii><json:string>S0923-5965(00)X0041-0</json:string></pii><pages><last>269</last><first>235</first></pages><issn><json:string>0923-5965</json:string></issn><issue>1–2</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Signal Processing: Image Communication</title><publicationDate>2000</publicationDate></host><categories><wos><json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string></wos></categories><publicationDate>2000</publicationDate><copyrightDate>2000</copyrightDate><doi><json:string>10.1016/S0923-5965(00)00030-8</json:string></doi><id>1FA901B770A0A97539A87D23170665B3489A0F54</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/fulltext/pdf</uri></json:item><json:item><original>true</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/fulltext/txt</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">Object-based multimedia content description schemes and applications for MPEG-7</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>2000</date></publicationStmt><notesStmt><note type="content">Fig. 1: Description of an image by proposed description scheme.</note><note type="content">Fig. 2: UML representation of the image description scheme.</note><note type="content">Fig. 3: Examples of different types of hierarchies.</note><note type="content">Fig. 4: (a) Example of objects in a large image (e.g. lakes in a satellite image). (b) Indexing hierarchy of objects based on their size.</note><note type="content">Fig. 5: (a) Object-definition hierarchy in the visual apprentice. (b) Original and automatically segmented baseball image. (c) Instance of the object-definition hierarchy for the batting class shown in (b).</note><note type="content">Fig. 6: Description of a video by proposed description scheme.</note><note type="content">Fig. 7: (a) Video object representation in AMOS. (b) Query interface of AMOS-search: query results, query canvas, and feature weights.</note><note type="content">Fig. 8: Description of a multimedia stream by proposed description scheme.</note><note type="content">Fig. 9: UML representation of the multimedia DS.</note><note type="content">Fig. 10: Relationships among components of the multimedia object “new program”.</note><note type="content">Fig. 11: Relationships among the components of multimedia object “Story i”.</note><note type="content">Fig. 12: Relationships among the components of multimedia object “Dialog”.</note><note type="content">Fig. 13: (a) Example of annotated home video sequence. (b) Examples of 1-P physical and 6-W semantic hierarchies.</note><note type="content">Fig. 14: UML representation of home media description scheme.</note><note type="content">Fig. 15: (a) Video objects in an archive on a subject-feature space. (b) Example of a subject ontology.</note><note type="content">Fig. 16: UML representation of proposed archive description scheme.</note><note type="content">Fig. 17: Overall architecture of MetaSEEk.</note><note type="content">Table 1: Feature classes and features</note><note type="content">Table 2: Examples of visual features and associated descriptors</note><note type="content">Table 3: Objects in each resolution layer</note><note type="content">Table 4: Examples of relation types and relations</note><note type="content">Table 5: Examples of new relation types and relations</note><note type="content">Table 6: New feature classes and features</note><note type="content">Table 7: Cluster feature classes and features</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a">Object-based multimedia content description schemes and applications for MPEG-7</title><author><persName><forename type="first">Ana B</forename><surname>Benitez</surname></persName><email>ana@ee.columbia.edu</email><note type="correspondence"><p>Corresponding author: Tel.: +1-212-854-7473; fax: +1-212-932-9421</p></note><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation></author><author><persName><forename type="first">Seungyup</forename><surname>Paek</surname></persName><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation></author><author><persName><forename type="first">Shih-Fu</forename><surname>Chang</surname></persName><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation></author><author><persName><forename type="first">Atul</forename><surname>Puri</surname></persName><affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</affiliation></author><author><persName><forename type="first">Qian</forename><surname>Huang</surname></persName><affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</affiliation></author><author><persName><forename type="first">John R</forename><surname>Smith</surname></persName><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation></author><author><persName><forename type="first">Chung-Sheng</forename><surname>Li</surname></persName><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation></author><author><persName><forename type="first">Lawrence D</forename><surname>Bergman</surname></persName><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation></author><author><persName><forename type="first">Charles N</forename><surname>Judice</surname></persName><affiliation>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</affiliation></author></analytic><monogr><title level="j">Signal Processing: Image Communication</title><title level="j" type="abbrev">IMAGE</title><idno type="pISSN">0923-5965</idno><idno type="PII">S0923-5965(00)X0041-0</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000"></date><biblScope unit="volume">16</biblScope><biblScope unit="issue">1–2</biblScope><biblScope unit="page" from="235">235</biblScope><biblScope unit="page" to="269">269</biblScope></imprint></monogr><idno type="istex">1FA901B770A0A97539A87D23170665B3489A0F54</idno><idno type="DOI">10.1016/S0923-5965(00)00030-8</idno><idno type="PII">S0923-5965(00)00030-8</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2000</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.</p></abstract><textClass><keywords scheme="keyword"><list><head>Keywords</head><item><term>MPEG-7</term></item><item><term>Multimedia description scheme</term></item><item><term>Multimedia representation</term></item><item><term>Object-based description</term></item><item><term>Multimedia</term></item><item><term>Image</term></item><item><term>Video</term></item><item><term>Home media</term></item><item><term>Archive</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2000">Published</change></revisionDesc></teiHeader></istex:fulltextTEI></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: ce:floats; body; tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"><istex:entity SYSTEM="gr1" NDATA="IMAGE" name="gr1"></istex:entity><istex:entity SYSTEM="gr2" NDATA="IMAGE" name="gr2"></istex:entity><istex:entity SYSTEM="gr3" NDATA="IMAGE" name="gr3"></istex:entity><istex:entity SYSTEM="gr4" NDATA="IMAGE" name="gr4"></istex:entity><istex:entity SYSTEM="gr5" NDATA="IMAGE" name="gr5"></istex:entity><istex:entity SYSTEM="gr6" NDATA="IMAGE" name="gr6"></istex:entity><istex:entity SYSTEM="gr7" NDATA="IMAGE" name="gr7"></istex:entity><istex:entity SYSTEM="gr8" NDATA="IMAGE" name="gr8"></istex:entity><istex:entity SYSTEM="gr9" NDATA="IMAGE" name="gr9"></istex:entity><istex:entity SYSTEM="gr10" NDATA="IMAGE" name="gr10"></istex:entity><istex:entity SYSTEM="gr11" NDATA="IMAGE" name="gr11"></istex:entity><istex:entity SYSTEM="gr12" NDATA="IMAGE" name="gr12"></istex:entity><istex:entity SYSTEM="gr13" NDATA="IMAGE" name="gr13"></istex:entity><istex:entity SYSTEM="gr14" NDATA="IMAGE" name="gr14"></istex:entity><istex:entity SYSTEM="gr15" NDATA="IMAGE" name="gr15"></istex:entity><istex:entity SYSTEM="gr16" NDATA="IMAGE" name="gr16"></istex:entity><istex:entity SYSTEM="gr17" NDATA="IMAGE" name="gr17"></istex:entity><istex:entity SYSTEM="fx1" NDATA="IMAGE" name="fx1"></istex:entity><istex:entity SYSTEM="fx2" NDATA="IMAGE" name="fx2"></istex:entity><istex:entity SYSTEM="fx3" NDATA="IMAGE" name="fx3"></istex:entity><istex:entity SYSTEM="fx4" NDATA="IMAGE" name="fx4"></istex:entity><istex:entity SYSTEM="fx5" NDATA="IMAGE" name="fx5"></istex:entity><istex:entity SYSTEM="fx6" NDATA="IMAGE" name="fx6"></istex:entity><istex:entity SYSTEM="fx7" NDATA="IMAGE" name="fx7"></istex:entity><istex:entity SYSTEM="fx8" NDATA="IMAGE" name="fx8"></istex:entity><istex:entity SYSTEM="fx9" NDATA="IMAGE" name="fx9"></istex:entity></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="fla"><item-info><jid>IMAGE</jid><aid>539</aid><ce:pii>S0923-5965(00)00030-8</ce:pii><ce:doi>10.1016/S0923-5965(00)00030-8</ce:doi><ce:copyright type="full-transfer" year="2000">Elsevier Science B.V.</ce:copyright></item-info><head><ce:title>Object-based multimedia content description schemes and applications for MPEG-7</ce:title><ce:author-group><ce:author><ce:given-name>Ana B</ce:given-name><ce:surname>Benitez</ce:surname><ce:cross-ref refid="AUT2"></ce:cross-ref><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref><ce:cross-ref refid="CORR1">*</ce:cross-ref><ce:e-address>ana@ee.columbia.edu</ce:e-address></ce:author><ce:author><ce:given-name>Seungyup</ce:given-name><ce:surname>Paek</ce:surname><ce:cross-ref refid="AUT3"></ce:cross-ref><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Shih-Fu</ce:given-name><ce:surname>Chang</ce:surname><ce:cross-ref refid="AUT4"></ce:cross-ref><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Atul</ce:given-name><ce:surname>Puri</ce:surname><ce:cross-ref refid="AUT5"></ce:cross-ref><ce:cross-ref refid="ORFB"><ce:sup>b</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Qian</ce:given-name><ce:surname>Huang</ce:surname><ce:cross-ref refid="AUT6"></ce:cross-ref><ce:cross-ref refid="ORFB"><ce:sup>b</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>John R</ce:given-name><ce:surname>Smith</ce:surname><ce:cross-ref refid="AUT7"></ce:cross-ref><ce:cross-ref refid="ORFC"><ce:sup>c</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Chung-Sheng</ce:given-name><ce:surname>Li</ce:surname><ce:cross-ref refid="AUT8"></ce:cross-ref><ce:cross-ref refid="ORFC"><ce:sup>c</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Lawrence D</ce:given-name><ce:surname>Bergman</ce:surname><ce:cross-ref refid="AUT9"></ce:cross-ref><ce:cross-ref refid="ORFC"><ce:sup>c</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Charles N</ce:given-name><ce:surname>Judice</ce:surname><ce:cross-ref refid="AUT10"></ce:cross-ref><ce:cross-ref refid="ORFD"><ce:sup>d</ce:sup></ce:cross-ref></ce:author><ce:affiliation id="ORFA"><ce:label>a</ce:label><ce:textfn>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</ce:textfn></ce:affiliation><ce:affiliation id="ORFB"><ce:label>b</ce:label><ce:textfn>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</ce:textfn></ce:affiliation><ce:affiliation id="ORFC"><ce:label>c</ce:label><ce:textfn>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</ce:textfn></ce:affiliation><ce:affiliation id="ORFD"><ce:label>d</ce:label><ce:textfn>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</ce:textfn></ce:affiliation><ce:correspondence id="CORR1"><ce:label>*</ce:label><ce:text>Corresponding author: Tel.: +1-212-854-7473; fax: +1-212-932-9421</ce:text></ce:correspondence></ce:author-group><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords class="keyword"><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>MPEG-7</ce:text></ce:keyword><ce:keyword><ce:text>Multimedia description scheme</ce:text></ce:keyword><ce:keyword><ce:text>Multimedia representation</ce:text></ce:keyword><ce:keyword><ce:text>Object-based description</ce:text></ce:keyword><ce:keyword><ce:text>Multimedia</ce:text></ce:keyword><ce:keyword><ce:text>Image</ce:text></ce:keyword><ce:keyword><ce:text>Video</ce:text></ce:keyword><ce:keyword><ce:text>Home media</ce:text></ce:keyword><ce:keyword><ce:text>Archive</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo><title>Object-based multimedia content description schemes and applications for MPEG-7</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>Object-based multimedia content description schemes and applications for MPEG-7</title></titleInfo><name type="personal"><namePart type="given">Ana B</namePart><namePart type="family">Benitez</namePart><affiliation>E-mail: ana@ee.columbia.edu</affiliation><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation><description>Corresponding author: Tel.: +1-212-854-7473; fax: +1-212-932-9421</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Seungyup</namePart><namePart type="family">Paek</namePart><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Shih-Fu</namePart><namePart type="family">Chang</namePart><affiliation>Image and Advanced Television Laboratory (ADVENT), Department of Electrical Engineering, Columbia University, 1312 S. W. Mudd, 500 West 120th Street, M.C. 4712, New York, NY 10027, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Atul</namePart><namePart type="family">Puri</namePart><affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Qian</namePart><namePart type="family">Huang</namePart><affiliation>AT&T Labs, 100 Schultz Drive – Middletown, Red Bank, NJ 07701, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">John R</namePart><namePart type="family">Smith</namePart><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Chung-Sheng</namePart><namePart type="family">Li</namePart><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Lawrence D</namePart><namePart type="family">Bergman</namePart><affiliation>IBM T.J Watson Research Center, 30 Saw Mill River Rd, Hawthorne, NY 10532, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Charles N</namePart><namePart type="family">Judice</namePart><affiliation>Eastman Kodak, 1447 St Paul Street, Rochester, NY 14653, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="Full-length article"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">2000</dateIssued><copyrightDate encoding="w3cdtf">2000</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">In this paper, we describe description schemes (DSs) for image, video, multimedia, home media, and archive content proposed to the MPEG-7 standard. MPEG-7 aims to create a multimedia content description standard in order to facilitate various multimedia searching and filtering applications. During the design process, special care was taken to provide simple but powerful structures that represent generic multimedia data. We use the extensible markup language (XML) to illustrate and exemplify the proposed DSs because of its interoperability and flexibility advantages. The main components of the image, video, and multimedia description schemes are object, feature classification, object hierarchy, entity-relation graph, code downloading, multi-abstraction levels, and modality transcoding. The home media description instantiates the former DSs proposing the 6-W semantic features for objects, and 1-P physical and 6-W semantic object hierarchies. The archive description scheme aims to describe collections of multimedia documents, whereas the former DSs only aim at individual multimedia documents. In the archive description scheme, the content of an archive is represented using multiple hierarchies of clusters, which may be related by entity-relation graphs. The hierarchy is a specific case of entity-relation graph using a containment relation. We explicitly include the hierarchy structure in our DSs because it is a natural way of defining composite objects, a more efficient structure for retrieval, and the representation structure used in MPEG-4. We demonstrate the feasibility and the efficiency of our description schemes by presenting applications that already use the proposed structures or will greatly benefit from their use. These applications are the visual apprentice, the AMOS-search system, a multimedia broadcast news browser, a storytelling system, and an image meta-search engine, MetaSEEk.</abstract><note type="content">Fig. 1: Description of an image by proposed description scheme.</note><note type="content">Fig. 2: UML representation of the image description scheme.</note><note type="content">Fig. 3: Examples of different types of hierarchies.</note><note type="content">Fig. 4: (a) Example of objects in a large image (e.g. lakes in a satellite image). (b) Indexing hierarchy of objects based on their size.</note><note type="content">Fig. 5: (a) Object-definition hierarchy in the visual apprentice. (b) Original and automatically segmented baseball image. (c) Instance of the object-definition hierarchy for the batting class shown in (b).</note><note type="content">Fig. 6: Description of a video by proposed description scheme.</note><note type="content">Fig. 7: (a) Video object representation in AMOS. (b) Query interface of AMOS-search: query results, query canvas, and feature weights.</note><note type="content">Fig. 8: Description of a multimedia stream by proposed description scheme.</note><note type="content">Fig. 9: UML representation of the multimedia DS.</note><note type="content">Fig. 10: Relationships among components of the multimedia object “new program”.</note><note type="content">Fig. 11: Relationships among the components of multimedia object “Story i”.</note><note type="content">Fig. 12: Relationships among the components of multimedia object “Dialog”.</note><note type="content">Fig. 13: (a) Example of annotated home video sequence. (b) Examples of 1-P physical and 6-W semantic hierarchies.</note><note type="content">Fig. 14: UML representation of home media description scheme.</note><note type="content">Fig. 15: (a) Video objects in an archive on a subject-feature space. (b) Example of a subject ontology.</note><note type="content">Fig. 16: UML representation of proposed archive description scheme.</note><note type="content">Fig. 17: Overall architecture of MetaSEEk.</note><note type="content">Table 1: Feature classes and features</note><note type="content">Table 2: Examples of visual features and associated descriptors</note><note type="content">Table 3: Objects in each resolution layer</note><note type="content">Table 4: Examples of relation types and relations</note><note type="content">Table 5: Examples of new relation types and relations</note><note type="content">Table 6: New feature classes and features</note><note type="content">Table 7: Cluster feature classes and features</note><subject><genre>Keywords</genre><topic>MPEG-7</topic><topic>Multimedia description scheme</topic><topic>Multimedia representation</topic><topic>Object-based description</topic><topic>Multimedia</topic><topic>Image</topic><topic>Video</topic><topic>Home media</topic><topic>Archive</topic></subject><relatedItem type="host"><titleInfo><title>Signal Processing: Image Communication</title></titleInfo><titleInfo type="abbreviated"><title>IMAGE</title></titleInfo><genre type="Journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">200009</dateIssued></originInfo><identifier type="ISSN">0923-5965</identifier><identifier type="PII">S0923-5965(00)X0041-0</identifier><part><date>200009</date><detail type="volume"><number>16</number><caption>vol.</caption></detail><detail type="issue"><number>1–2</number><caption>no.</caption></detail><extent unit="issue pages"><start>1</start><end>294</end></extent><extent unit="pages"><start>235</start><end>269</end></extent></part></relatedItem><identifier type="istex">1FA901B770A0A97539A87D23170665B3489A0F54</identifier><identifier type="DOI">10.1016/S0923-5965(00)00030-8</identifier><identifier type="PII">S0923-5965(00)00030-8</identifier><accessCondition type="use and reproduction" contentType="">© 2000Elsevier Science B.V.</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Elsevier Science B.V., ©2000</recordOrigin></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/1FA901B770A0A97539A87D23170665B3489A0F54/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">ENGINEERING, ELECTRICAL & ELECTRONIC</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI></enrichments><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000685 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000685 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:1FA901B770A0A97539A87D23170665B3489A0F54
|texte= Object-based multimedia content description schemes and applications for MPEG-7
}}
| This area was generated with Dilib version V0.6.32. |  |